الفهرس 
IntroductionOnly 14 pages are availabe for public view
 |  | from | 112 |  |  |
| | | from | 112 | | |
Abstract
Identification and control of nonlinear systems such as robots have been a difficult challenging problem for decades. Having a good performance for the robots had been a major objective for many of the scientific research conducted over many decades. One of these considerable systems is the Three Links Manipulator system, which represents many of the robots used in industry nowadays. In this thesis, the mathematical model of three links manipulator system will be derived. we consider and rearrange the coordinate frames to have the transformation matrices between any considered frames to the original frame. Also, Dynamic Modeling will be used to derive the Kinetic Energy, Potential Energy. Then, Lagrange’s equation will be applied to have equations of motion. A conventional controller (PID) will be applied to control the manipulator, then the robot will be simulated using MATLAB, showing the simulation results using PID controller. After that, we will introduce our proposed controller (Artificial Neural Network Based PID) to control the manipulator. Neural network control algorithms are developed to solve the nonlinear problems for compensating robot manipulator control with uncertainties, so that accurate position could be achieved. The back propagation algorithm is used for training a two layered feed-forward artificial neural network. The proposed controller is simply combining the ANN with other conventional control method, it provides the network with more data about the structure and the behavior of the system. The neural network is trained with the data generated by PID controller. Then the mathematical model of the system will be simulated under the control of the proposed controller. It will be studied and discussed to judge whether it could achieve good performance during the motion of the robot or not. Then, Comparisons between system performances under the control of each controller (ANN and PID) will be evaluated and discussed. Also, comparisons between the proposed controller with related works is done. The simulation results proved the effectiveness of the proposed technique in comparison with the conventional (PID) controller and other related works.